Abstract: A computer implemented method for generating a response to a received electronic message. A generative AI is prompted to analyse the electronic message and to generate intent data indicative of an intent associated with the electronic message and data-identifier data indicative of one or more predetermined data identifiers present in the electronic message. The electronic message is analysed to identify and retrieve client data associated with one or more parties associated with the electronic message. The method includes Verifying the retrieved client data includes data corresponding to the generated data-identifier data. If so, query an ERP system with the verified data-identifier data to extract ERP data corresponding to the predetermined data identifiers of which the data-identifier data is indicative, select a response-message template using the intent data, populate the selected response-message template with the ERP data, and present the populated response-message template to a user for approval.

Abstract: A computer-implemented chatbot including a prompt generation module, a large language model (LLM) module, and an answer generation module. The prompt generation modules generates an initial prompt based on a prompt template combined with a received user query. The initial prompt includes information source data specifying sources of factual information, conversation history data, and failed response data. The initial prompt is input to the LLM module, which is configured to generate an output and communicate the output to the answer generation module. The answer generation modules determines if the output is a plan to answer a user query. If so, relevant data is retrieved from external database or more APIs specified in the information source data. A further prompt is generated for answering the user query and input to the LLM module. The answer generation module repeats its tasks until a suitable answer to the user query is output.

Abstract: A computer implemented method of detecting hallucination in a large language model (LLM) output. A message is received. A prompt is generated for an LLM including the message and an instruction to generate an output identifying predetermined content in the message. The prompt is passed through an LLM to generate the output. The output is processed in accordance with a hallucination detection process to identify if any predetermined content identified by the LLM in the output is potentially hallucinated.

Abstract: A system and computer implemented method for detecting hallucination in output of a generative AI system. User input is received specifying a query or task relating to information contained in a data object. A first vector representation of the user input and a second vector representation of the data object are generated. The first and second vector representations are compared to identify parts of the data object which match the query or task. An input is generated for a generative AI system with the user input and the parts of the data object. The input is input to a generative AI system. An output produced by the generative AI system is analysed to determine if the output contains information also present in the data object. If not, an error process is initiated. If so, the output is produced by the generative AI system.

Abstract: A system for generalizing the format of instructional content for mobile delivery is disclosed. The system includes a processor configured to identify institutional content in a client-specific data file, and further configured to store, in a memory, the identified institutional content as generalized institutional content. The system also includes a communications module configured to receive, from a mobile device, a request for the generalized institutional content. The processor is configured to provide, to the mobile device in response to the request, the generalized institutional content in a format configured for display on the mobile device. Methods and machine-readable mediums are also disclosed.

Abstract: A graphical user interface system is provided. The system includes a display and a processor, coupled to the display, configured to display a window, in an initial position. Upon receiving a window docking input by a user indicating a request to dock the window at a predefined docking point, the processor is configured to dock the window at the predefined docking point. The docking of the window at the predefined docking point includes hiding a portion of the window. Upon receiving a window docking input by a user indicating a request to simultaneously dock each of a plurality of windows at a predefined docking point, the processor is configured to dock each of the plurality of windows at a corresponding position on the predefined docking point, including hiding a portion of each of the plurality of windows. Methods and computer-readable mediums are also provided.

Abstract: A system for integrating user-specific institutional content for mobile delivery is disclosed. The system includes a communications module configured to receive, from a mobile device, a request for target institutional content based on source institutional content and an identification of a user. The system also includes a processor configured to obtain, from a memory, the target institutional content based on the source institutional content and the identification of the user, and further configured to provide, to the mobile device in response to the request, the generalized institutional content in a format configured for display on the mobile device. Methods and machine-readable mediums are also disclosed.

Abstract: A graphical user interface system is provided. The system includes a display and a processor, coupled to the display, configured to display a window, in an initial position. Upon receiving a window docking input by a user indicating a request to dock the window at a predefined docking point, the processor is configured to dock the window at the predefined docking point. The docking of the window at the predefined docking point includes hiding a portion of the window. Upon receiving a window docking input by a user indicating a request to simultaneously dock each of a plurality of windows at a predefined docking point, the processor is configured to dock each of the plurality of windows at a corresponding position on the predefined docking point, including hiding a portion of each of the plurality of windows. Methods and computer-readable mediums are also provided.

Abstract: In certain embodiments, a graphical user interface system is provided. The system includes a display and a processor, coupled to the display, configured to display a plurality of windows. The processor is configured to simultaneously receive from a user a plurality of window action inputs, each window action input associated with a corresponding window, indicating requests to conduct actions with the corresponding windows. Each window action input is separately provided by the user. Each window includes a frame portion and a content portion including an object having at least one predetermined function and capable of receiving an input configured to active the predetermined function. When the processor receives a window adjustment input for the object from a user indicating a request to adjust the window, the window is configured to be adjusted. The window adjustment input is different than the input. Methods and computer-readable mediums are also provided.

Abstract: A system for integrating user-specific institutional content for mobile delivery is disclosed. The system includes a communications module configured to receive, from a mobile device, a request for target institutional content based on source institutional content and an identification of a user. The system also includes a processor configured to obtain, from a memory, the target institutional content based on the source institutional content and the identification of the user, and further configured to provide, to the mobile device in response to the request, the generalized institutional content in a format configured for display on the mobile device. Methods and machine-readable mediums are also disclosed.

Abstract: A system for generalizing the format of instructional content for mobile delivery is disclosed. The system includes a processor configured to identify institutional content in a client-specific data file, and further configured to store, in a memory, the identified institutional content as generalized institutional content. The system also includes a communications module configured to receive, from a mobile device, a request for the generalized institutional content. The processor is configured to provide, to the mobile device in response to the request, the generalized institutional content in a format configured for display on the mobile device. Methods and machine-readable mediums are also disclosed.